© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23780
    Prev
    Next
    INDEX
    Explanations

    Code/filepaths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģéģį
    -0.30
    quire
    -0.27
    èĻı
    -0.26
    æ¹ľ
    -0.26
    åĬ¡
    -0.25
     whisper
    -0.25
    éĴŀ
    -0.25
    automation
    -0.24
    _Command
    -0.24
    èĥ½ä¸įèĥ½
    -0.24
    POSITIVE LOGITS
    locks
    0.27
    æѧ
    0.26
    é¢Ŀ
    0.26
     Syrians
    0.26
    صب
    0.25
    ÃŃlia
    0.24
     der
    0.24
    lug
    0.24
    踣
    0.24
    der
    0.24
    Activations Density 0.010%

    No Known Activations